In [17]:
import pandas as pd
import numpy as np
import seaborn as sns
import geopandas as gpd
import matplotlib.pyplot as plt
%matplotlib inline
import matplotlib.colors as colors
import matplotlib.patches as mpatches
from pandas import cut
from matplotlib import colormaps as cmap
import folium
%matplotlib inline
plt.rcParams['figure.figsize'] = (10, 8)
plt.style.use("ggplot")
In [18]:
health_cols = [
'Census tract 2010 ID',
'County Name',
'State/Territory',
'Total population',
'Percent American Indian / Alaska Native',
'Percent Asian', 'Percent Black or African American alone',
'Percent Hispanic or Latino',
'Percent Native Hawaiian or Pacific',
'Percent other races',
'Percent White',
'Coronary heart disease among adults aged greater than or equal to 18 years',
'Coronary heart disease among adults aged greater than or equal to 18 years (percentile)',
'Current asthma among adults aged greater than or equal to 18 years',
'Current asthma among adults aged greater than or equal to 18 years (percentile)',
'Diagnosed diabetes among adults aged greater than or equal to 18 years',
'Diagnosed diabetes among adults aged greater than or equal to 18 years (percentile)',
'Low life expectancy (percentile)',
'Percent age 10 to 64',
'Percent age over 64',
'Percent age under 10'
]
In [19]:
health_stats = pd.read_csv(r"C:\\New_499_Code\\499_Cleaned_Abbreviated_CEJST_Disadvantaged_Communities_Data.csv", usecols=health_cols)
health_stats.head(2)
Out[19]:
| Census tract 2010 ID | County Name | State/Territory | Percent Black or African American alone | Percent American Indian / Alaska Native | Percent Asian | Percent Native Hawaiian or Pacific | Percent White | Percent Hispanic or Latino | Percent other races | ... | Percent age 10 to 64 | Percent age over 64 | Total population | Current asthma among adults aged greater than or equal to 18 years (percentile) | Current asthma among adults aged greater than or equal to 18 years | Diagnosed diabetes among adults aged greater than or equal to 18 years (percentile) | Diagnosed diabetes among adults aged greater than or equal to 18 years | Coronary heart disease among adults aged greater than or equal to 18 years (percentile) | Coronary heart disease among adults aged greater than or equal to 18 years | Low life expectancy (percentile) | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 1001020100 | Autauga County | Alabama | 0.07 | 0.0 | 0.0 | 0.00 | 0.83 | 0.01 | 0.0 | ... | 0.76 | 0.13 | 1993.0 | 57.0 | 990.0 | 60.0 | 1130.0 | 59.0 | 640.0 | 89.0 |
| 1 | 1001020200 | Autauga County | Alabama | 0.57 | 0.0 | 0.0 | 0.01 | 0.38 | 0.01 | 0.0 | ... | 0.73 | 0.14 | 1959.0 | 82.0 | 1100.0 | 83.0 | 1420.0 | 49.0 | 590.0 | 65.0 |
2 rows × 21 columns
In [20]:
CEJST_shapefile_path = r"C:\New_499_Code\assets\cb_2021_us_tract_500k\cb_2021_us_tract_500k.shp"
CEJST_Shapefile = gpd.read_file(CEJST_shapefile_path)
# Filter the GeoDataFrame because it takes 20 minutes to run otherwise
filtered_CEJST_Shapefile = CEJST_Shapefile[CEJST_Shapefile['STATE_NAME'].isin(['Tennessee'])]
filtered_CEJST_Shapefile.head(2)
--------------------------------------------------------------------------- KeyboardInterrupt Traceback (most recent call last) Cell In[20], line 2 1 CEJST_shapefile_path = r"C:\New_499_Code\assets\cb_2021_us_tract_500k\cb_2021_us_tract_500k.shp" ----> 2 CEJST_Shapefile = gpd.read_file(CEJST_shapefile_path) 4 # Filter the GeoDataFrame because it takes 20 minutes to run otherwise 5 filtered_CEJST_Shapefile = CEJST_Shapefile[CEJST_Shapefile['STATE_NAME'].isin(['Tennessee'])] File c:\School\Spring2024\Spring2024Env\lib\site-packages\geopandas\io\file.py:297, in _read_file(filename, bbox, mask, rows, engine, **kwargs) 294 else: 295 path_or_bytes = filename --> 297 return _read_file_fiona( 298 path_or_bytes, from_bytes, bbox=bbox, mask=mask, rows=rows, **kwargs 299 ) 301 else: 302 raise ValueError(f"unknown engine '{engine}'") File c:\School\Spring2024\Spring2024Env\lib\site-packages\geopandas\io\file.py:395, in _read_file_fiona(path_or_bytes, from_bytes, bbox, mask, rows, where, **kwargs) 391 df = pd.DataFrame( 392 [record["properties"] for record in f_filt], columns=columns 393 ) 394 else: --> 395 df = GeoDataFrame.from_features( 396 f_filt, crs=crs, columns=columns + ["geometry"] 397 ) 398 for k in datetime_fields: 399 as_dt = None File c:\School\Spring2024\Spring2024Env\lib\site-packages\geopandas\geodataframe.py:641, in GeoDataFrame.from_features(cls, features, crs, columns) 638 if hasattr(feature, "__geo_interface__"): 639 feature = feature.__geo_interface__ 640 row = { --> 641 "geometry": shape(feature["geometry"]) if feature["geometry"] else None 642 } 643 # load properties 644 properties = feature["properties"] File c:\School\Spring2024\Spring2024Env\lib\site-packages\shapely\geometry\geo.py:101, in shape(context) 99 return LinearRing(ob["coordinates"]) 100 elif geom_type == "polygon": --> 101 return Polygon(ob["coordinates"][0], ob["coordinates"][1:]) 102 elif geom_type == "multipoint": 103 return MultiPoint(ob["coordinates"]) File c:\School\Spring2024\Spring2024Env\lib\site-packages\shapely\geometry\polygon.py:230, in Polygon.__new__(self, shell, holes) 228 return shell 229 else: --> 230 shell = LinearRing(shell) 232 if holes is not None: 233 if len(holes) == 0: 234 # shapely constructor cannot handle holes=[] File c:\School\Spring2024\Spring2024Env\lib\site-packages\shapely\geometry\polygon.py:104, in LinearRing.__new__(self, coordinates) 99 if len(coordinates) == 0: 100 # empty geometry 101 # TODO better constructor + should shapely.linearrings handle this? 102 return shapely.from_wkt("LINEARRING EMPTY") --> 104 geom = shapely.linearrings(coordinates) 105 if not isinstance(geom, LinearRing): 106 raise ValueError("Invalid values passed to LinearRing constructor") File c:\School\Spring2024\Spring2024Env\lib\site-packages\shapely\decorators.py:77, in multithreading_enabled.<locals>.wrapped(*args, **kwargs) 75 for arr in array_args: 76 arr.flags.writeable = False ---> 77 return func(*args, **kwargs) 78 finally: 79 for arr, old_flag in zip(array_args, old_flags): File c:\School\Spring2024\Spring2024Env\lib\site-packages\shapely\creation.py:171, in linearrings(coords, y, z, indices, out, **kwargs) 169 coords = _xyz_to_coords(coords, y, z) 170 if indices is None: --> 171 return lib.linearrings(coords, out=out, **kwargs) 172 else: 173 return simple_geometries_1d(coords, indices, GeometryType.LINEARRING, out=out) KeyboardInterrupt:
In [ ]:
#merge the environmental data with the shapefile, keep all columns
health_stats = filtered_CEJST_Shapefile.merge(health_stats, left_on='NAMELSADCO', right_on='County Name', how='left')
health_stats.head(2)
Out[ ]:
| STATEFP | COUNTYFP | TRACTCE | AFFGEOID | GEOID | NAME | NAMELSAD | STUSPS | NAMELSADCO | STATE_NAME | ... | Percent age 10 to 64 | Percent age over 64 | Total population | Current asthma among adults aged greater than or equal to 18 years (percentile) | Current asthma among adults aged greater than or equal to 18 years | Diagnosed diabetes among adults aged greater than or equal to 18 years (percentile) | Diagnosed diabetes among adults aged greater than or equal to 18 years | Coronary heart disease among adults aged greater than or equal to 18 years (percentile) | Coronary heart disease among adults aged greater than or equal to 18 years | Low life expectancy (percentile) | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 47 | 037 | 015805 | 1400000US47037015805 | 47037015805 | 158.05 | Census Tract 158.05 | TN | Davidson County | Tennessee | ... | 0.72 | 0.10 | 5566.0 | 40.0 | 930.0 | 20.0 | 810.0 | 19.0 | 440.0 | 20.0 |
| 1 | 47 | 037 | 015805 | 1400000US47037015805 | 47037015805 | 158.05 | Census Tract 158.05 | TN | Davidson County | Tennessee | ... | 0.72 | 0.19 | 7593.0 | 24.0 | 869.0 | 38.0 | 950.0 | 49.0 | 590.0 | 18.0 |
2 rows × 35 columns
In [ ]:
#check to see if health_stats is a geoDataFrame
type(health_stats)
Out[ ]:
geopandas.geodataframe.GeoDataFrame
In [ ]:
health_stats_filtered = health_stats[health_stats['STATE_NAME'] == 'Tennessee']
In [ ]:
In [ ]:
print(health_stats.crs)
EPSG:4269
In [ ]:
from sklearn.preprocessing import MinMaxScaler
health_stats = health_stats.applymap(lambda x: 1 if x is True else (0 if x is False else x))
# Normalize the columns using MinMaxScaler (scaling values health_stats 0 and 1)
scaler = MinMaxScaler()
# Selecting the columns to scale
columns_to_scale = [
'Coronary heart disease among adults aged greater than or equal to 18 years',
'Current asthma among adults aged greater than or equal to 18 years',
'Diagnosed diabetes among adults aged greater than or equal to 18 years'
]
# Scaling the columns
health_stats[columns_to_scale] = scaler.fit_transform(health_stats[columns_to_scale])
# Calculating the Health Score by combining the scaled metrics
# Using equal weights for now; this can be adjusted based on importance
health_stats['Health Score'] = (
health_stats['Coronary heart disease among adults aged greater than or equal to 18 years'] +
health_stats['Current asthma among adults aged greater than or equal to 18 years'] +
health_stats['Diagnosed diabetes among adults aged greater than or equal to 18 years']
) / 3 # Dividing by 3
# Displaying the results
print(health_stats[['Census tract 2010 ID', 'County Name', 'Health Score']])
C:\Users\Kassidi\AppData\Local\Temp\ipykernel_32636\4246406488.py:2: FutureWarning: DataFrame.applymap has been deprecated. Use DataFrame.map instead. health_stats = health_stats.applymap(lambda x: 1 if x is True else (0 if x is False else x))
Census tract 2010 ID County Name Health Score 0 37057060101 Davidson County 0.220487 1 37057060102 Davidson County 0.245786 2 37057060201 Davidson County 0.318352 3 37057060202 Davidson County 0.365253 4 37057060203 Davidson County 0.280844 ... ... ... ... 314983 48313000200 Madison County 0.318275 314984 48313000300 Madison County 0.308442 314985 48313000400 Madison County 0.326354 314986 51113930100 Madison County 0.337121 314987 51113930200 Madison County 0.324577 [314988 rows x 3 columns]
In [ ]:
from shapely.ops import unary_union
# Create a copy of the GeoDataFrame
health_stats_copy = health_stats.copy()
# Use 'unary_union' to combine multiple geometries for the same county
health_stats_copy = health_stats_copy.groupby(['County Name', 'State/Territory']).agg(
{
'Total population': 'mean',
'Percent American Indian / Alaska Native': 'mean',
'Percent Asian': 'mean',
'Percent Black or African American alone': 'mean',
'Percent Hispanic or Latino': 'mean',
'Percent Native Hawaiian or Pacific': 'mean',
'geometry': lambda x: unary_union(x), # Combine multiple geometries
'Coronary heart disease among adults aged greater than or equal to 18 years': 'mean',
'Coronary heart disease among adults aged greater than or equal to 18 years (percentile)': 'mean',
'Current asthma among adults aged greater than or equal to 18 years': 'mean',
'Current asthma among adults aged greater than or equal to 18 years (percentile)': 'mean',
'Diagnosed diabetes among adults aged greater than or equal to 18 years': 'mean',
'Diagnosed diabetes among adults aged greater than or equal to 18 years (percentile)': 'mean',
'Low life expectancy (percentile)': 'mean',
'Percent age 10 to 64': 'mean',
'Percent age over 64': 'mean',
'Percent age under 10': 'mean',
'Health Score': 'mean'
}
).reset_index()
# Convert the dataframe back to a GeoDataFrame
health_stats_copy = gpd.GeoDataFrame(health_stats_copy)
# Check if the GeoDataFrame is correct
type(health_stats_copy)
Out[ ]:
geopandas.geodataframe.GeoDataFrame
In [ ]:
county_health_map = health_stats_copy.set_geometry('geometry')
# Create the map with the first layer (Health Score)
county_health_map = health_stats_copy.explore(
column="Health Score",
scheme="naturalbreaks",
legend=False,
k=5,
tooltip=False,
popup=['County Name', 'Health Score'],
legend_kwds=dict(colorbar=False),
name="Health Score",
width="80%",
height="500px"
)
# Add the tile layer to the map
folium.TileLayer("CartoDB positron", show=False).add_to(county_health_map)
# Add the second layer (Energy Burden) to the same map
health_stats_copy.explore(
m=county_health_map,
column="Coronary heart disease among adults aged greater than or equal to 18 years",
scheme="naturalbreaks",
legend=False,
k=5,
tooltip=False,
popup=['County Name', 'Coronary heart disease among adults aged greater than or equal to 18 years'],
legend_kwds=dict(colorbar=False),
name="Coronary heart disease among adults aged greater than or equal to 18 years",
cmap="Reds"
)
# Add a Layer Control to toggle layers
folium.LayerControl().add_to(county_health_map)
# Display the map
county_health_map
Out[ ]:
Make this Notebook Trusted to load map: File -> Trust Notebook
In [ ]:
#create a horizontal bar chart for the top 5 counties with highest diabetes rates
top_5_diabetes = health_stats_copy.nlargest(5, 'Diagnosed diabetes among adults aged greater than or equal to 18 years')
top_5_diabetes = top_5_diabetes.sort_values('Diagnosed diabetes among adults aged greater than or equal to 18 years', ascending=True)
plt.barh(top_5_diabetes['County Name'], top_5_diabetes['Diagnosed diabetes among adults aged greater than or equal to 18 years'], color='skyblue')
plt.xlabel('Diagnosed diabetes among adults aged greater than or equal to 18 years')
plt.ylabel('County Name')
plt.title('Top 5 Counties with Highest Diabetes Rates')
plt.show()
In [ ]:
#visualize the distribution of health scores
plt.hist(health_stats_copy['Health Score'], bins=20, color='purple')
plt.xlabel('Health Score')
plt.ylabel('Frequency')
plt.title('Distribution of Health Scores')
plt.show()
In [22]:
%pip install nbconvert
Collecting nbconvert Downloading nbconvert-7.16.4-py3-none-any.whl.metadata (8.5 kB) Requirement already satisfied: beautifulsoup4 in c:\school\spring2024\spring2024env\lib\site-packages (from nbconvert) (4.12.3) Requirement already satisfied: bleach!=5.0.0 in c:\school\spring2024\spring2024env\lib\site-packages (from nbconvert) (6.1.0) Requirement already satisfied: defusedxml in c:\school\spring2024\spring2024env\lib\site-packages (from nbconvert) (0.7.1) Requirement already satisfied: jinja2>=3.0 in c:\school\spring2024\spring2024env\lib\site-packages (from nbconvert) (3.1.3) Requirement already satisfied: jupyter-core>=4.7 in c:\school\spring2024\spring2024env\lib\site-packages (from nbconvert) (5.7.1) Requirement already satisfied: jupyterlab-pygments in c:\school\spring2024\spring2024env\lib\site-packages (from nbconvert) (0.3.0) Requirement already satisfied: markupsafe>=2.0 in c:\school\spring2024\spring2024env\lib\site-packages (from nbconvert) (2.1.4) Requirement already satisfied: mistune<4,>=2.0.3 in c:\school\spring2024\spring2024env\lib\site-packages (from nbconvert) (3.0.2) Requirement already satisfied: nbclient>=0.5.0 in c:\school\spring2024\spring2024env\lib\site-packages (from nbconvert) (0.9.0) Requirement already satisfied: nbformat>=5.7 in c:\school\spring2024\spring2024env\lib\site-packages (from nbconvert) (5.9.2) Requirement already satisfied: packaging in c:\school\spring2024\spring2024env\lib\site-packages (from nbconvert) (23.2) Requirement already satisfied: pandocfilters>=1.4.1 in c:\school\spring2024\spring2024env\lib\site-packages (from nbconvert) (1.5.1) Requirement already satisfied: pygments>=2.4.1 in c:\school\spring2024\spring2024env\lib\site-packages (from nbconvert) (2.17.2) Requirement already satisfied: tinycss2 in c:\school\spring2024\spring2024env\lib\site-packages (from nbconvert) (1.2.1) Requirement already satisfied: traitlets>=5.1 in c:\school\spring2024\spring2024env\lib\site-packages (from nbconvert) (5.14.1) Requirement already satisfied: six>=1.9.0 in c:\school\spring2024\spring2024env\lib\site-packages (from bleach!=5.0.0->nbconvert) (1.16.0) Requirement already satisfied: webencodings in c:\school\spring2024\spring2024env\lib\site-packages (from bleach!=5.0.0->nbconvert) (0.5.1) Requirement already satisfied: platformdirs>=2.5 in c:\school\spring2024\spring2024env\lib\site-packages (from jupyter-core>=4.7->nbconvert) (4.1.0) Requirement already satisfied: pywin32>=300 in c:\school\spring2024\spring2024env\lib\site-packages (from jupyter-core>=4.7->nbconvert) (306) Requirement already satisfied: jupyter-client>=6.1.12 in c:\school\spring2024\spring2024env\lib\site-packages (from nbclient>=0.5.0->nbconvert) (8.6.0) Requirement already satisfied: fastjsonschema in c:\school\spring2024\spring2024env\lib\site-packages (from nbformat>=5.7->nbconvert) (2.19.1) Requirement already satisfied: jsonschema>=2.6 in c:\school\spring2024\spring2024env\lib\site-packages (from nbformat>=5.7->nbconvert) (4.21.1) Requirement already satisfied: soupsieve>1.2 in c:\school\spring2024\spring2024env\lib\site-packages (from beautifulsoup4->nbconvert) (2.5) Requirement already satisfied: attrs>=22.2.0 in c:\school\spring2024\spring2024env\lib\site-packages (from jsonschema>=2.6->nbformat>=5.7->nbconvert) (23.2.0) Requirement already satisfied: jsonschema-specifications>=2023.03.6 in c:\school\spring2024\spring2024env\lib\site-packages (from jsonschema>=2.6->nbformat>=5.7->nbconvert) (2023.12.1) Requirement already satisfied: referencing>=0.28.4 in c:\school\spring2024\spring2024env\lib\site-packages (from jsonschema>=2.6->nbformat>=5.7->nbconvert) (0.33.0) Requirement already satisfied: rpds-py>=0.7.1 in c:\school\spring2024\spring2024env\lib\site-packages (from jsonschema>=2.6->nbformat>=5.7->nbconvert) (0.17.1) Requirement already satisfied: python-dateutil>=2.8.2 in c:\school\spring2024\spring2024env\lib\site-packages (from jupyter-client>=6.1.12->nbclient>=0.5.0->nbconvert) (2.8.2) Requirement already satisfied: pyzmq>=23.0 in c:\school\spring2024\spring2024env\lib\site-packages (from jupyter-client>=6.1.12->nbclient>=0.5.0->nbconvert) (25.1.2) Requirement already satisfied: tornado>=6.2 in c:\school\spring2024\spring2024env\lib\site-packages (from jupyter-client>=6.1.12->nbclient>=0.5.0->nbconvert) (6.4) Downloading nbconvert-7.16.4-py3-none-any.whl (257 kB) ---------------------------------------- 0.0/257.4 kB ? eta -:--:-- ----------- ---------------------------- 71.7/257.4 kB 1.9 MB/s eta 0:00:01 ---------------------------------------- 257.4/257.4 kB 3.9 MB/s eta 0:00:00 Installing collected packages: nbconvert Successfully installed nbconvert-7.16.4 Note: you may need to restart the kernel to use updated packages.
[notice] A new release of pip is available: 24.0 -> 24.3.1 [notice] To update, run: python.exe -m pip install --upgrade pip
In [24]:
#save entire notebook to html
import os
import nbformat
from nbconvert import HTMLExporter
notebook_filename = 'C:\\New_499_Code\\health_analysis2.html'
In [ ]:
#export the notebook to html
html_exporter = HTMLExporter()
content, info = html_exporter.from_filename('C:\\New_499_Code\\health_analysis.ipynb')
--------------------------------------------------------------------------- FileNotFoundError Traceback (most recent call last) Cell In[28], line 4 1 #export the notebook to html 3 html_exporter = HTMLExporter() ----> 4 content, info = html_exporter.from_filename('C:\\New_499_Code\\health_analysis3.ipynb') File c:\School\Spring2024\Spring2024Env\lib\site-packages\nbconvert\exporters\templateexporter.py:386, in TemplateExporter.from_filename(self, filename, resources, **kw) 382 def from_filename( # type:ignore[override] 383 self, filename: str, resources: dict[str, t.Any] | None = None, **kw: t.Any 384 ) -> tuple[str, dict[str, t.Any]]: 385 """Convert a notebook from a filename.""" --> 386 return super().from_filename(filename, resources, **kw) File c:\School\Spring2024\Spring2024Env\lib\site-packages\nbconvert\exporters\exporter.py:191, in Exporter.from_filename(self, filename, resources, **kw) 187 resources["metadata"]["name"] = notebook_name 188 resources["metadata"]["path"] = path 190 modified_date = datetime.datetime.fromtimestamp( --> 191 os.path.getmtime(filename), tz=datetime.timezone.utc 192 ) 193 # datetime.strftime date format for ipython 194 if sys.platform == "win32": File C:\Python310\lib\genericpath.py:55, in getmtime(filename) 53 def getmtime(filename): 54 """Return the last modification time of a file, reported by os.stat().""" ---> 55 return os.stat(filename).st_mtime FileNotFoundError: [WinError 2] The system cannot find the file specified: 'C:\\New_499_Code\\health_analysis3.ipynb'
In [ ]: